{"id":"https://openalex.org/W2967558504","doi":"https://doi.org/10.1109/cec.2019.8790001","title":"Deep Multi-agent Reinforcement Learning in a Common-Pool Resource System","display_name":"Deep Multi-agent Reinforcement Learning in a Common-Pool Resource System","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2967558504","doi":"https://doi.org/10.1109/cec.2019.8790001","mag":"2967558504"},"language":"en","primary_location":{"id":"doi:10.1109/cec.2019.8790001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2019.8790001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029804107","display_name":"Hanwei Zhu","orcid":"https://orcid.org/0000-0002-0894-0561"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Hanwei Zhu","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025856575","display_name":"Michael Kirley","orcid":"https://orcid.org/0000-0002-6030-858X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Michael Kirley","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029804107"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":1.0201,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84515601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"518","issue":null,"first_page":"142","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7899488806724548},{"id":"https://openalex.org/keywords/common-pool-resource","display_name":"Common-pool resource","score":0.6890622973442078},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6875658631324768},{"id":"https://openalex.org/keywords/tragedy-of-the-commons","display_name":"Tragedy of the commons","score":0.6640777587890625},{"id":"https://openalex.org/keywords/social-dilemma","display_name":"Social dilemma","score":0.6118717193603516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5997236967086792},{"id":"https://openalex.org/keywords/commons","display_name":"Commons","score":0.5979520678520203},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49923133850097656},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4883589446544647},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.46474310755729675},{"id":"https://openalex.org/keywords/social-learning","display_name":"Social learning","score":0.4643550217151642},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44182470440864563},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.41971462965011597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3381654918193817},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2465629279613495},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.21286699175834656},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.16263985633850098},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.14448437094688416},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11601302027702332},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11295381188392639}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7899488806724548},{"id":"https://openalex.org/C83729063","wikidata":"https://www.wikidata.org/wiki/Q12055115","display_name":"Common-pool resource","level":2,"score":0.6890622973442078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875658631324768},{"id":"https://openalex.org/C15517945","wikidata":"https://www.wikidata.org/wiki/Q334622","display_name":"Tragedy of the commons","level":3,"score":0.6640777587890625},{"id":"https://openalex.org/C187206662","wikidata":"https://www.wikidata.org/wiki/Q55607920","display_name":"Social dilemma","level":2,"score":0.6118717193603516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5997236967086792},{"id":"https://openalex.org/C49427245","wikidata":"https://www.wikidata.org/wiki/Q9828451","display_name":"Commons","level":2,"score":0.5979520678520203},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49923133850097656},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4883589446544647},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.46474310755729675},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.4643550217151642},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44182470440864563},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.41971462965011597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3381654918193817},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2465629279613495},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.21286699175834656},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.16263985633850098},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.14448437094688416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11601302027702332},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11295381188392639},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cec.2019.8790001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2019.8790001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W568318363","https://openalex.org/W1498720233","https://openalex.org/W1515851193","https://openalex.org/W1587892878","https://openalex.org/W1589747210","https://openalex.org/W1757796397","https://openalex.org/W1793282889","https://openalex.org/W2041484817","https://openalex.org/W2046959667","https://openalex.org/W2053616263","https://openalex.org/W2062663664","https://openalex.org/W2072455842","https://openalex.org/W2093057598","https://openalex.org/W2093376316","https://openalex.org/W2105834378","https://openalex.org/W2113346360","https://openalex.org/W2132979098","https://openalex.org/W2135232136","https://openalex.org/W2145339207","https://openalex.org/W2147571562","https://openalex.org/W2165150801","https://openalex.org/W2167062553","https://openalex.org/W2173248099","https://openalex.org/W2264743790","https://openalex.org/W2395575420","https://openalex.org/W2518075538","https://openalex.org/W2580175322","https://openalex.org/W2594794854","https://openalex.org/W2616746986","https://openalex.org/W2739364177","https://openalex.org/W2742108445","https://openalex.org/W2789102605","https://openalex.org/W2895865957","https://openalex.org/W2911795125","https://openalex.org/W2919115771","https://openalex.org/W2963000099","https://openalex.org/W2963407617","https://openalex.org/W2963658727","https://openalex.org/W2963689090","https://openalex.org/W2963864421","https://openalex.org/W2964345382","https://openalex.org/W3103559770","https://openalex.org/W3124616391","https://openalex.org/W4210788696","https://openalex.org/W4233654598","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W4302570325","https://openalex.org/W6629825631","https://openalex.org/W6635062730","https://openalex.org/W6637967152","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6712181171","https://openalex.org/W6732665253","https://openalex.org/W6735011893","https://openalex.org/W6738796088","https://openalex.org/W6741436713"],"related_works":["https://openalex.org/W1958607777","https://openalex.org/W114908060","https://openalex.org/W2044237124","https://openalex.org/W3202622097","https://openalex.org/W2986871228","https://openalex.org/W2226637984","https://openalex.org/W3164731623","https://openalex.org/W2899091653","https://openalex.org/W2811498230","https://openalex.org/W2415868115"],"abstract_inverted_index":{"In":[0,53,90],"complex":[1],"social-ecological":[2],"systems,":[3,27],"multiple":[4],"agents":[5,98,142,165],"with":[6,103,129],"diverse":[7],"objectives":[8],"take":[9],"actions":[10],"that":[11,141,164],"affect":[12],"the":[13,17,47,51,58,81,91,96,156,162,174,190],"long-term":[14],"dynamics":[15,36],"of":[16,25,50,60,68,80,94,120,148,173,176],"system.":[18,73],"Common":[19],"pool":[20,71],"resources":[21],"are":[22,31,37],"a":[23,39,42,65,69,85,100,117,122],"subset":[24],"such":[26],"where":[28],"property":[29],"rights":[30],"typically":[32],"poorly":[33],"defined":[34],"and":[35,132,151],"unknown":[38],"priori,":[40],"creating":[41],"social":[43],"dilemma":[44],"reflected":[45],"by":[46],"well-known":[48],"`tragedy":[49],"commons.'":[52],"this":[54],"paper,":[55],"we":[56],"investigated":[57],"efficacy":[59],"deep":[61,101,158,180],"reinforcement":[62,181],"learning":[63,127,159,182],"in":[64,116,146,189],"multi-agent":[66],"setting":[67],"common":[70],"resource":[72],"We":[74],"used":[75,99,185],"an":[76],"abstract":[77],"mathematical":[78],"model":[79,128],"system,":[82],"represented":[83],"as":[84],"partially-observable":[86],"general-sum":[87],"Markov":[88],"game.":[89],"first":[92],"set":[93,119],"experiments,":[95,121],"independent":[97],"Q-Network":[102],"discrete":[104],"action":[105,133],"spaces":[106,134],"to":[107,187],"guide":[108],"decision-making.":[109],"However,":[110],"significant":[111],"shortcomings":[112],"were":[113],"evident.":[114],"Consequently,":[115],"second":[118,157],"Deep":[123],"Deterministic":[124],"Policy":[125],"Gradient":[126],"continuous":[130],"state":[131],"guided":[135],"agent":[136],"learning.":[137],"Simulation":[138],"results":[139],"show":[140],"performed":[143],"significantly":[144],"better":[145],"terms":[147],"both":[149],"sustainability":[150],"economic":[152],"goals":[153],"when":[154],"using":[155],"model.":[160],"Despite":[161],"fact":[163],"do":[166],"not":[167],"have":[168],"perfect":[169],"foresight":[170],"nor":[171],"understanding":[172],"implications":[175],"their":[177],"`harvesting'":[178],"efforts,":[179],"can":[183],"be":[184],"effectively":[186],"`learn":[188],"commons'.":[191]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}